Determining pose for use with digital watermarking, fingerprinting and augmented reality

Abstract

Image recognition and augmented reality experiences utilize auxiliary data extracted from an image or video, or image fingerprints, or a combination of both. One claim recites a method comprising: receiving a plurality of imagery frames captured by a device sensor; identifying a plurality of key points in each of the plurality of imagery frames; resolving image pose by utilizing relative relationships of the key points between different frames of the plurality of frames; modifying imagery of at least one of the plurality of frames based on resolved image pose; and deriving a fingerprint from modified imagery. Of course other claims and combinations are provided as well.

Description

APPLICATION FIELD[0001]This application claims the benefit of U.S. Provisional Patent Application No. 61 / 719,920, filed Oct. 29, 2012. This application is also related to U.S. Provisional Patent Application No. 61 / 749,767, filed Jan. 7, 2013. Each of the above patent documents is hereby incorporated herein by reference in its entirety.TECHNICAL FIELD[0002]This disclosure relates to digital signal processing, image rendering (including Raster Image Processing for print), image recognition, data signal detection, and computer generated graphics in conjunction with live image capture and recognition (e.g., Augmented Reality).BACKGROUND AND SUMMARY[0003]There are a variety of ways to encode machine readable information on objects, and in particular, on printed objects. Conventional visible data carriers for printed media include various forms of bar codes, including monochrome (e.g., black and white) 1D and 2D bar codes, as well as newer higher density codes that use additional colors t...

AI Technical Summary

Benefits of technology

This patent is about a method for inserting hidden data into printed objects, such as barcodes and logos, that can be easily detected and read by a computer. The method uses a combination of digital watermarking and image fingerprinting to maintain the aesthetic value and information content of the image. The hidden data can be used for applications where there is a need to convey variable digital data in the printed object, such as advertisements or product labels. The method takes advantage of the gap between the limit of human visual perception and the limit of an image sensor to insert auxiliary data without impacting other visual information on the object. The printed objects can also be used for content identification and related applications.

Problems solved by technology

For hidden data insertion, the challenge is to insert the data in the human-sensor perception gap so that it can be widely detected across many consumer devices.

Of course, for certain security applications, more expensive printers and image scanners can be designed to insert security features and expand the gamut of the scanning equipment used to detect such features.

However, the human-device perception gap is smaller for more widely deployed sensors, such as those commonly used in mobile devices like smart phones and tablet PCs.

Images